出眾的外貌是人際交往的重要因素，也代表職場與社交優勢，由於人們對外貌重視形成醫學美容發展急遽發展，2008年醫學美容已成為全球第三大產業；其中雷射除斑為微整形美容治療的主要項目。現今雷射除斑是經由皮膚科醫師透過專業判斷與經驗操作，在配戴護目鏡操作雷射手持裝置過程中，不易透過肉眼辨識斑點。因此本研究主要應用醫學影像技術，探討(1)皮膚影像擷取裝置設計，(2)雀斑偵測之影像處理方法和(3)系統驗證分析。本研究完成(1)皮膚影像擷取裝置雛型和(2)皮膚雀斑之影像分析。根據實驗結果統計分析得到(1)自動化雀斑影像分析具有靈敏度95%，特異性81%和面積辨識率為71%；(2)辨識速率在解析度640x480時為0.3s，解析度1294x966時為1s，可搭配此裝置進行動態偵測雀斑。未來可從(1)彩色影像處理與分析方法，(2)演算法優化和(3)建立雀斑與非雀斑影資料庫著手進一步加以探討。

Good appearance is one of important factors affecting the interpersonal activity, as well as the working and social advantages. The importance of appearance brings development of medical cosmetology with the rapid advance. Medical cosmetic industry has been the world's third-largest industry in 2008. To remove the freckles using laser is the major item in micro cosmetic surgery. During the laser spot removing surgery, it is heavily dependent on the experiences and profession of doctor in operation. It is difficult to visually identify the pigment spots and nature skin for the doctor with the goggles. Therefore, the purpose of this study is to develop the skin freckles detection system using medical imaging technology on the topics of (1) skin image capture device design,(2) the freckles detection of image processing method, and (3) system performance analysis. In this study, (1) Freckles image acquisition device prototype and (2) skin freckles image analysis are accomplished. From statistical analysis of the experimental results, it is shown that (1) the sensitivity and specificity of the freckle detection system are 95% and 81%, respectively. The freckle area recognition rate is about 71%. (2) The detection speed of the system is about 0.3 sec with image resolution of 640x480 and 1 sec with 1294x966. It can be applied for freckle detection dynamically with laser. Some points such as (1) the color image processing and analysis, (2) algorithm optimization, and (3) the building of freckles and non-freckles image database may be further investigated.

[1] 台灣1111人力銀行。職場愛美指數大調查。網址：http://winner.1111.com.tw/zone/pr/headline.asp?autono=1578。2007
[2] 戴伯芬、陳萱蘋。春光乍現：微整型美容的科技不老神話分析。2011年文化研究學會年會。文化研究學會。台北。 2011
[3] 黃彥臻。2009~10醫療器材產業年鑑。 工研院產經與趨勢研究中心。2009
[4] R. R. Anderson, J. A. Parrish, “Selective photothermolysis: precise microsurgery by selective absorption of pulsed radiation,” Science, New Series, Vol.220, No. 4596, pp.524-527, April 1983
[5] 張慈映。醫用雷射潛力應用市場分析。工研院IEK。 2007
[6] 台大皮膚科部。實用皮膚醫學。第二版。 台北：國立台灣大學醫學院。 Nov. 2006.
[7] E. N. Marieb, J. Mallatt, P. B. Wilhelm, Human Anatomy, 5th, Benjamin Cummings, 2007
[8] Mitchel P. Goldman, Robert A. Weiss, etc, Advabced techiniques in dermatologic surgery, Francis, 2006
[9] Mitchel P. Goldman, Cutaneous and Cosmetic Laser Surgery, 1st, MOSBY Elsevier, 2006
[10] W. Gonzalez。數位影像處理。第三版。謬紹剛譯。台北：台灣培生教育。2009
[11] C. Yao, Image Cosmetics: An Automatic Skin Exfoliation Framework on Static Images, Thesis. University of California, Santa Barbara, December 2005
[12] P. Carli , E. Quercioli , S. Sestini , M. Stante , L. Ricci , G. Brunasso and V. DE Giorgi, “Pattern analysis, not simplified algorithms, is the most reliable method for teaching dermoscopy for melanoma diagnosis to residents in dermatology,” BritishJournal of Dermatolog., vol. 148, no. 5, pp. 981–984, 2003.
[13] U. Lipowezky, S. Cahen, “Automatic freckles detection and retouching”, proc., Electrical and Electronics Engineers in Israel, 2008. IEEEI 2008. IEEE 25th Convention of, pp. 142 – 146, 2008
[14] C. Steger, M. Ulrich, C. Wiedemann, Machine Vision Algorithms and Applications, Wiley-VCH, October 2007
[15] 孟如松、蔡瑞康。偏振光皮膚鏡數字圖像分析技術的研究及在色素性皮損診斷中的探討。中國體視學與圖像分析。第11卷，第2期。2006
[16] P. Armstrong, M. L. Wastie。醫學影像診斷學。初版。 鄭慶明譯。台北：合記。2001
[17] A. V. Oppenheim, R. W. Schafer, Discrete-Time Signal Processing, Prentice Hall, pp. 140-210, 1999
[18] 洪欣瑜。雷射醫學美容給您美麗新人生。新光醫訊。184期。2007
[19] Li-Ming Jian, Design and Development of Skin Pores Detection System, M. S. Thesis, National Cheng Kung University, 2012
[20] 陳順宇、鄭碧娥。統計學。第三版。台北：華泰書局。1998